© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3943
    Prev
    Next
    INDEX
    Explanations

    code snippets including javascript or html

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.67
    例文帳に追加
    -0.56
     FetchType
    -0.50
     "..\..\..\
    -0.45
    Personendaten
    -0.45
     مشين
    -0.44
     yoda
    -0.41
     الاطلاع
    -0.40
    Referències
    -0.40
    AccessFile
    -0.39
    POSITIVE LOGITS
     onOptions
    0.64
     onClose
    0.63
    mtable
    0.63
    onShow
    0.60
    onMouse
    0.60
    isVisible
    0.60
    isSelected
    0.60
    MouseEvent
    0.60
    hasClass
    0.59
     isSelected
    0.59
    Activations Density 10.199%

    No Known Activations